[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-456685-105":59,"doc-detail-456685-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","determining-accuracy-of-diagnosis-and-management-of-common-presenting-semen-analyses-using-artificial-intelligence-programs-research-study","Determining accuracy of diagnosis and management of common presenting semen analyses using artificial intelligence programs - Research study","","Evaluates how accurately two AI programs, Google Bard and Bing, interpret common semen analysis findings and propose next steps for suspected male infertility. AI systems were given semen volume, pH, concentration, and sperm motility data spanning normal to abnormal patterns including obstructive and non-obstructive azoospermia, oligospermia, and related conditions. Study personnel assessed diagnostic accuracy of each program’s top three diagnoses and its recommended patient actions based on predetermined clinical interpretations. Bard showed higher overall accuracy for analytical outputs, while both programs recommended physician discussion.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/determining-accuracy-of-diagnosis-and-management-of-common-presenting-semen-analyses-using-artificial-intelligence-programs-research-study/456685/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/determining-accuracy-of-diagnosis-and-management-of-common-presenting-semen-analyses-using-artificial-intelligence-programs-research-study/456685.png","ImageObject",300,407,{"name":92,"@type":93},"Jiven","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-05","2026-09-30",true,{"@type":102,"interactionType":103,"userInteractionCount":14},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What was the objective of the study comparing Bard and Bing?","Question",{"text":112,"@type":113},"To evaluate the diagnostic accuracy of two commonly used AI programs by checking whether they correctly interpret a sample semen analysis and recommend appropriate next steps after diagnosis.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What inputs were used for the AI programs in the study?",{"text":117,"@type":113},"Each AI program received semen volume, pH, concentration, and sperm motility percentage data, covering entirely normal and abnormal cases including obstructive and non-obstructive azoospermia and other semen abnormalities.",{"name":119,"@type":110,"acceptedAnswer":120},"What were the main accuracy findings for diagnosis and next steps?",{"text":121,"@type":113},"Bing showed 29% accuracy for semen analysis interpretation with partially correct responses in 57% of cases, while Bard had higher analytical accuracy (50%). For next steps, both programs recommended discussing results with a physician, with next-step accuracy reported as 100% for the AI outputs.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},456685,1791200583,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":14,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":24,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":144},1099513958607,"https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399","Determining accuracy of diagnosis and management of common presenting semen analyses using artificial intelligence programs  \nBaylor Price1, Madeline Helm1, Christopher M. Deibert2  \n1College of Medicine, University of Nebraska Medical Center, Omaha, NE, USA; 2Division of Urologic Surgery, University of Nebraska Medical Center, Omaha, NE, USA  \nContributions: (I) Conception and design: CM Deibert; (II) Administrative support: All authors; (III) Provision of study materials or patients: None; (IV) Collection and assembly of data: B Price, M Helm; (V) Data analysis and interpretation: All authors; (VI) Manuscript writing: All authors; (VII) Final  \napproval of manuscript: All authors.  \nCorrespondence to: Madeline Helm, BS. College of Medicine, University of Nebraska Medical Center, SSP2015, Omaha, NE 68198, USA.  \n[Email: mhelm@unmc.edu](Email: mhelm@unmc.edu).  \nBackground: Over the past few years, artificial intelligence (AI) platforms have rapidly gained popularity within medicine. While AI has been applied in various subspecialties of urology, its role in evaluating malefactor infertility has not been explored. The objective of this study was to evaluate the diagnostic accuracy of two commonly used AI programs, Google’s “Bard” and Bing. This study aimed to assess each program’s accuracy in correctly diagnosing a sample patient’s semen analysis results and recommending appropriate  \nnext steps following diagnosis.  \nMethods: Each respective AI program was given a set of data which included semen volume, pH, concentration, and sperm motility as a percentage along with a command to list the three most likely diagnoses and the next steps the patient should take . The data sets ranged from entirely normal to abnormal with clearly obstructive and non-obstructive azoospermia, teratozoospermia, oligospermia, orasthenospermia. Study personnel determined the clinical diagnostic accuracy of both Bard’s and Bing’s semen  \nanalysis interpretations. No patient data was utilized for this study.  \nResults: Bing resulted in only 29% accuracy of interpretation while 57% of results provided partially correct responses. First, second, and third, diagnoses provided resulted in 43%, 29% and 43% accuracy, respectively. Each analysis was 100% accurate in the next steps the patient should take and recommended discussing results with a physician 100% of the time. Bard was slightly more accurate regarding semen analysis with 50% accuracy. First, second, and third diagnoses provided resulted in 75%, 25%, and 25% accuracy, respectively. Bard had 75% accuracy regarding next steps but also had a 100% accuracy rating for  \nrecommending discussing results with a physician.  \nConclusions: Overall, Bard was more accurate in providing correct analytical information regarding semen analysis (50% vs. 29%) . Bard generated consistently accurate first diagnosis (75% vs. 43%) . Bing resulted in increased accuracy regarding next steps (100% vs. 75%). Both programs recommended discussing semen analysis results with a physician. Overall, Bing and Bard are not capable of consistently providing patients with accurate analysis, diagnosis, or next steps when given a sample semen analysis. Specific training sets must be developed to provide with accurate interpretation of their urological results in a user-friendly  \nformat that can be further addressed with their physician.  \nKeywords: Semen analysis; artificial intelligence (AI); male infertility; spermatozoa; machine learning  \nSubmitted Jul 19, 2025. Accepted for publication Sep 16, 2025. Published online Dec 24, 2025.  \ndoi: 10.21037/tau-2025-508  \nView this article at: [https://dx.doi.org/10.21037/tau-2025-508](https://dx.doi.org/10.21037/tau-2025-508)  \n© AME Publishing Company. Transl Androl Urol 2025;14(12):3867-3871 | [https://dx.doi.org/10.21037/tau-2025-508](https://dx.doi.org/10.21037/tau-2025-508)  \n3868 Price et al. AI accuracy in diagnosing semen analyses  \nIntroduction  \nArtificial intelligence (AI) platf","cbCainmCp7irtnnR","https://ap.wps.com/l/cbCainmCp7irtnnR","pdf",238132,"English","# Background\n# Methods\n# Results\n# Conclusions\n# Introduction\n## Highlight box\n### Key findings\n### What is known and what is new","[{\"question\":\"What was the objective of the study comparing Bard and Bing?\",\"answer\":\"To evaluate the diagnostic accuracy of two commonly used AI programs by checking whether they correctly interpret a sample semen analysis and recommend appropriate next steps after diagnosis.\"},{\"question\":\"What inputs were used for the AI programs in the study?\",\"answer\":\"Each AI program received semen volume, pH, concentration, and sperm motility percentage data, covering entirely normal and abnormal cases including obstructive and non-obstructive azoospermia and other semen abnormalities.\"},{\"question\":\"What were the main accuracy findings for diagnosis and next steps?\",\"answer\":\"Bing showed 29% accuracy for semen analysis interpretation with partially correct responses in 57% of cases, while Bard had higher analytical accuracy (50%). For next steps, both programs recommended discussing results with a physician, with next-step accuracy reported as 100% for the AI outputs.\"}]","Determining accuracy of diagnosis and management of common presenting semen analyses using artificial intelligence programs - Research study | PDF",1790746719,13]